Data-Driven Tensor Train Gradient Cross Approximation for Hamilton–Jacobi–Bellman Equations

DOI10.1137/22m1498401zbMath1523.49037arXiv2205.05109MaRDI QIDQ6054276

Dante Kalise, Sergey V. Dolgov, Luca Saluzzi

Publication date: 27 September 2023

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2205.05109

zbMATH Keywords

optimal feedback controldynamic programmingHamilton-Jacobi-Bellman equationstensor decompositionhigh-dimensional approximation

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Optimal feedback synthesis (49N35) Dynamic programming (90C39) Optimality conditions for problems involving ordinary differential equations (49K15) Hamilton-Jacobi equations (35F21)

Cites Work

• Unnamed Item
• Unnamed Item
• Tensor-Train Decomposition
• TT-cross approximation for multidimensional arrays
• Computation of extreme eigenvalues in higher dimensions using block tensor train format
• Low-rank tensor completion by Riemannian optimization
• Suboptimal feedback control of PDEs by solving HJB equations on adaptive sparse grids
• Parallel tensor sampling in the hierarchical Tucker format
• Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures
• Mitigating the curse of dimensionality: sparse grid characteristics method for optimal feedback control and HJB equations
• A continuous analogue of the tensor-train decomposition
• Quasioptimality of maximum-volume cross interpolation of tensors
• A new scheme for the tensor representation
• Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations
• Stable als approximation in the TT-format for rank-adaptive tensor completion
• Approximation rates for the hierarchical tensor format in periodic Sobolev spaces
• Nonlinear feedback controllers and compensators: a state-dependent Riccati equation approach
• Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs
• State-dependent Riccati equation feedback stabilization for nonlinear PDEs
• Approximation of optimal control problems for the Navier-Stokes equation via multilinear HJB-POD
• Spectral Tensor-Train Decomposition
• Riemannian Optimization for High-Dimensional Tensor Completion
• A literature survey of low-rank tensor approximation techniques
• The Alternating Linear Scheme for Tensor Optimization in the Tensor Train Format
• Alternating Minimal Energy Methods for Linear Systems in Higher Dimensions
• Tensor Spaces and Numerical Tensor Calculus
• Robust Feedback Control of Nonlinear PDEs by Numerical Approximation of High-Dimensional Hamilton--Jacobi--Isaacs Equations
• Order Reduction Methods for Solving Large-Scale Differential Matrix Riccati Equations
• A Curse-of-Dimensionality-Free Numerical Method for Solution of Certain HJB PDEs
• The Max-Plus Finite Element Method for Solving Deterministic Optimal Control Problems: Basic Properties and Convergence Analysis
• Range-Separated Tensor Format for Many-Particle Modeling
• Solving high-dimensional partial differential equations using deep learning
• Adaptive Deep Learning for High-Dimensional Hamilton--Jacobi--Bellman Equations
• Tensor Decomposition Methods for High-dimensional Hamilton--Jacobi--Bellman Equations
• Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
• Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks
• SympOCnet: Solving Optimal Control Problems with Applications to High-Dimensional Multiagent Path Planning Problems
• Approximating Optimal feedback Controllers of Finite Horizon Control Problems Using Hierarchical Tensor Formats
• A Numerical Comparison of Different Solvers for Large-Scale, Continuous-Time Algebraic Riccati Equations and LQR Problems
• A tree structure algorithm for optimal control problems with state constraints
• Approximative Policy Iteration for Exit Time Feedback Control Problems Driven by Stochastic Differential Equations using Tensor Train Format
• Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm

This page was built for publication: Data-Driven Tensor Train Gradient Cross Approximation for Hamilton–Jacobi–Bellman Equations